Multimodal

Multimodal LLMs are evolving from vision-language to tri-modality that see, hear, and read, yet pipelines and benchmarks remain English-centric and compute-heavy. The tutorial offers an overview of this emerging research area for multilingual multimodality across text, speech, and vision under limited data/compute budgets, synthesizing foundations, recent multilingual models (PALO, Maya), speech-text LLMs. We cover low-cost data creation/curation; adapter stacks for tri-modal alignment; culture-aware evaluation beyond English and hands on resources for fine-tuning a compact multilingual VLM and wiring a speech->text->LLM pipeline. The content will be delivered as an interactive half-day tutorial, designed for researchers and practitioners working on multilingual, multimodal AI in low-resource language settings.

The rapid advancement of Deepfake technologies and video manipulation tools poses a critical challenge to multimedia forensics, judicial evidence integrity, and information authenticity. Current detectors rely on single-modality signals, treating appearance, geometry, and motion independently. However, advanced generators maintain within-modality consistency while producing cross-modal contradictions, which are forensically discriminative but invisible to any single-modal detector. We propose CAM-VFD, a Cross-Attention Multimodal Video Forgery Detection framework that models cross-modal contradiction as a directional forensic signal. The framework uses a cross-attention fusion mechanism in which CLIP-based appearance representations serve as queries against VideoMAE motion features and MiDaS depth features, enabling the identification of contradictions between visual, temporal, and geometric evidence. We examine this design through cross-modal attention discrepancy analysis, observing statistically separable real and fake distributions ($p<0.001$, Cohen's $d=0.68$). Experimental results on two generative video benchmarks indicate consistent performance, with 95.31% Top-1 accuracy on GenVidBench and 93.43% accuracy, 90.63% F1-score, and 96.56% AUROC on GenVideo. Moreover, CAM-VFD demonstrates stable performance under compression, noise, blur, and adversarial perturbations, suggesting that cross-modal reasoning may improve robustness in media forensics. The code is publicly available at \url{https://github.com/Hoda-Osama/CAM-VFD/tree/main}.

Memory has become an increasingly important component of agentic systems, as these systems are expected to reason over long-term experience. However, prior work has largely focused on unimodal memory, leaving multimodal memory relatively underexplored despite its central role in real-world applications. Compared with unimodal settings, multimodal memory introduces additional challenges, including heterogeneous input integration, person-centric information alignment, and evidence aggregation across different granularities. We present PyraVid, a hierarchical multimodal memory framework inspired by Event Segmentation Theory from cognitive science. PyraVid organizes long videos into a coarse-to-fine pyramid structure, enabling structured memory access and effective evidence aggregation. It further supports structure-guided memory expansion with pruning, allowing the retrieval of related events with strong causal connectivity but low semantic similarity while reducing noise. Experiments on multiple long-video understanding benchmarks show that PyraVid consistently improves performance across datasets, model scales, and question types, highlighting the effectiveness of hierarchical multimodal memory for long-horizon reasoning.

Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident errors more than uncertain ones and no signal that ties confidence to the quality of visual evidence, a gap that becomes especially severe under corrupted or ambiguous inputs where models continue to report high confidence on incorrect answers. We introduce Ranking-Aware Calibration (RAC), a training-time framework that supervises confidence using two comparison signals that group-based RL already produces at no additional labeling cost. The ranking-aware group loss enforces that a better rollout receives higher confidence than a worse one within the same prompt. The clean--corrupted pairwise loss enforces that confidence attenuates as visual evidence degrades. Because the ranking signal forces the policy to distinguish between correct and incorrect reasoning paths, it also reinforces task accuracy beyond what correctness rewards alone produce. Both losses require no external confidence annotations and integrate naturally with group-based RL post-training. We instantiate RAC on Qwen2.5-VL and InternVL-3.5 backbones and evaluate on six multimodal reasoning benchmarks under clean and corrupted inputs. Empirical results show that the ranking-aware loss substantially improves task accuracy by teaching the policy to discriminate between better and worse reasoning, while the pairwise corruption loss reduces calibration error under degraded inputs. Their combination achieves the best calibration across all tested backbones while improving accuracy in the majority of settings.

Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the model alone. However, self-contained MLLMs are constrained by finite parametric knowledge, static training corpora, and limited perceptual resolution, creating a practical ceiling in dynamic open-world forensics -- particularly for real-time event verification requiring external clues and forgery segmentation demanding fine-grained scrutiny of local manipulations. To address these limitations, we shift from scaling up the self-contained model toward reaching beyond it. We propose \textbf{OmniVL-Guard Pro}, a tool-augmented agent that extends unified forensics from closed-world prediction to open-world clues-driven reasoning. OmniVL-Guard Pro integrates a tool environment spanning real-time event search, local cropping and zooming, edge-anomaly screening, face detection, video frame extraction, and SAM3-based segmentation. To generate high-quality tool-reasoning trajectories, we introduce \textbf{Tree-Structured Self-Evolving Tool Trajectory Generation}, which produces diverse trajectories through seed guidance, guider-free self-evolution, and weakly-hinted hard sample synthesis, yielding the Full-Spectrum Tool Reasoning (FSTR) dataset for training. We further propose \textbf{Checker-Guided Agentic Reinforcement Learning} (CGARL), which provides process-level supervision to penalize cases where the answer is correct but the reasoning is distorted. Extensive experiments demonstrate that OmniVL-Guard Pro achieves state-of-the-art performance across various tasks, and exhibits strong zero-shot generalization. The FSTR dataset and code for OmniVL-Guard Pro will be publicly released at https://github.com/shen8424/OmniVL-Guard-Pro.

Multimodal emotion recognition aims to integrate text, audio, and video sources to understand human affective states. Although multimodal large language models excel at multimodal reasoning, they typically treat emotion categories as independent labels, ignoring the rich hierarchical taxonomy of human psychology. Moreover, lacking external contextual knowledge makes them highly susceptible to over-interpreting noisy cues, further complicating fine-grained emotion classification. To address these issues, we propose \textbf{HyperEmo-RAG}, a retrieval-augmented generation framework that leverages a structured emotional knowledge base. Our framework introduces two key innovations. 1) Hierarchical hyperbolic grounding. Recognizing the inherent hierarchical tree structure of emotion taxonomies, we jointly embed hierarchical emotion labels and multimodal samples into a continuous hyperbolic space (Poincaré ball) and design a hierarchical beam-search deliberation process that progressively retrieves samples from coarse to fine-grained levels. 2) Structured evidence injection. Based on the retrieved evidence, we construct an evidence graph and inject the structured knowledge as explicit cognitive context into the LLM through a Tree-Aware Attention mechanism and an EmotionGraphFormer, preserving the integrity of graph-structured information. Experiments on multiple datasets demonstrate that HyperEmo-RAG significantly outperforms existing methods.

Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before producing a final result. Existing benchmarks, however, often evaluate tool use, computer use, and multimodal reasoning in isolation, leaving a gap between benchmark settings and end-to-end omni-modal tool use in the real world. To address this gap, we introduce MM-ToolBench, a benchmark and evaluation harness for task-oriented omni-modal tool use. MM-ToolBench contains 100 executable tasks from two macro task families, Customer Service and Intelligent Creation, covering 20 subcategory slices and supported by 27 MCP servers with 324 tools. The central design of MM-ToolBench is closed-loop multimodal verification: agents must execute tools, inspect rendered or transformed artifacts, and self-correct when outputs fail task-specific requirements. To make such evaluation scalable and verifiable, MM-ToolBench couples MCP-based execution with task-specific grounded evaluators and a semi-automated construction pipeline for scenario discovery, task instantiation, evaluator synthesis, and human audit. Experiments on 15 contemporary agentic models show that MM-ToolBench remains highly challenging: Claude Opus 4.6, commonly regarded as one of the strongest coding-agent models, achieves only 32.0% task success, far below the 94.0% human benchmark. We envision MM-ToolBench as a practical foundation for evaluating and advancing next-generation omni-modal tool-using agents through closed-loop multimodal verification.

Multimodal sentiment analysis relies on textual, acoustic, and visual signals, yet real-world data often suffer from modality missing and quality imbalance. Existing methods generate features for modality missing from available ones, but differences in expression mechanisms and sentiment dynamics across modalities may cause the generated features to deviate from true distributions and mislead prediction. In addition, unreliable modalities may dominate fusion, resulting in representation shift across modality combinations and unstable sentiment representations. To address these challenges, we propose a two-level reference alignment framework. The framework introduces stable references at the feature representation and sentiment decision levels to improve robustness under modality missing. First-level reference alignment leverages complete-modality samples to constrain representations and align different modality combinations into a shared sentiment space. Second-level reference alignment enforces cross-modal consistency at the decision level by suppressing unreliable modalities through prototype retrieval and voting. As a result, the framework maintains stable and reliable sentiment predictions under diverse missing-modality patterns. Experiments on CMU-MOSI and CMU-MOSEI show consistent improvements across various missing-modality settings. Under full-modality input, the proposed method achieves state-of-the-art performance, with ACC of 86.28% and 85.88%, and F1 of 86.24% and 85.86%.

Cross-modality recognition has many important applications in science, law enforcement and entertainment. Popular methods to bridge the modality gap include reducing the distributional differences of representations of different modalities, learning indistinguishable representations or explicit modality transfer. The first two approaches suffer from the loss of discriminant information while removing the modality-specific variations. The third one heavily relies on the successful modality transfer, could face catastrophic performance drop when explicit modality transfers are not possible or difficult. To tackle this problem, we proposed a compact encoder-decoder neural module (cmUNet) to learn modality-agnostic representations while retaining identity-related information. This is achieved through cross-modality transformation and in-modality reconstruction, enhanced by an adversarial/perceptual loss which encourages indistinguishability of representations in the original sample space. For cross-modality matching, we propose MarrNet where cmUNet is connected to a standard feature extraction network which takes as inputs the modality-agnostic representations and outputs similarity scores for matching. We validated our method on five challenging tasks, namely Raman-infrared spectrum matching, cross-modality person re-identification and heterogeneous (photo-sketch, visible-near infrared and visible-thermal) face recognition, where MarrNet showed superior performance compared to state-of-the-art methods. Furthermore, it is observed that a cross-modality matching method could be biased to extract discriminant information from partial or even wrong regions, due to incompetence of dealing with modality gaps, which subsequently leads to poor generalization. We show that robustness to occlusions can be an indicator of whether a method can well bridge the modality gap.

Multimodal pre-training demonstrates strong generalization performance, but this paradigm is often impractical in domains where paired data are scarce. A promising alternative is post-hoc multimodal alignment, which aligns separately pre-trained unimodal encoders using a limited number of paired examples. However, existing methods focus primarily on aligning global representations, missing patch-token relations. This may hinder transfer to tasks that require fine-grained cross-modal matching beyond coarse sample-level semantics. To address this issue, we propose a post-hoc alignment method that learns token-level cross-modal structure using relative representations. Specifically, we represent images and texts through their token-level similarities to a set of learnable anchors in each modality space, which are trained to induce consistent cross-modal similarity patterns for matched pairs. Despite learning only the anchors without heavy projection layers, our approach consistently outperforms existing methods in zero-shot classification, cross-modal retrieval, and zero-shot segmentation by a substantial margin. This highlights the importance of modeling fine-grained cross-modal structure for effective post-hoc multimodal alignment with limited paired data.

Collaborative game-based learning environments offer rich opportunities for small-group knowledge construction, yet automatically predicting student collaboration satisfaction remains challenging. A critical barrier is modality degradation: in educational deployments, individual modalities such as eye gaze exhibit inconsistent informativeness across student cohorts, causing implicit attention-based fusion to produce brittle multimodal representations. We propose the Affinity-Aligned Multimodal Learning Analytics (AAMLA) framework, whose core contribution is the Cross-modal Affinity-guided Modality Alignment (CAMA) module, which explicitly models inter-modal relationships via affinity matrices and enforces cross-modal consistency through contrastive learning, enabling adaptive suppression of uninformative modalities without discarding them. AAMLA further applies modality-specific projection layers to map heterogeneous features, including facial action units, head pose, eye gaze, and interaction trace logs, into a unified semantic space prior to alignment. Experiments on 50 middle school students in the EcoJourneys collaborative learning environment demonstrate consistent improvements over unimodal baselines and prior cross-attention approaches under standard and modality degradation conditions, with SHAP and t-SNE analyses confirming that CAMA produces robust, interpretable cross-modal representations for student collaboration modeling.

Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependencies with linear computational complexity. Moreover, an Axial-Relation Guided Fusion Module is designed to explicitly model global cross-modal correlations along horizontal and vertical axes, enabling efficient feature fusion between optical and elevation modalities. Extensive experiments conducted on the ISPRS Vaihingen and Potsdam datasets demonstrate that our ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency. The code will be made publicly available at \url{https://github.com/oucailab/ARG-Mamba}.

This paper addresses the challenge of integrating 3D meshes as a native modality within Multimodal Large Language Models (MLLMs). Diffusion-based large reconstruction models decouple semantic understanding from geometric reasoning, operating as stateless reconstructors conditioned on dense 2D pixel priors. Recent MLLM-based methods treat the 3D modality as an external output rather than a native component of the multimodal sequence, making incremental adaptations without a systematic analysis of how geometric manifolds align with MLLM feature spaces. We introduce EVA01, a unified framework that extends the modality boundary of MLLMs to natively incorporate 3D mesh understanding, generation, and context-aware editing. Built upon a Mixture-of-Transformers (MoT) architecture, EVA01 decouples the model into a pre-trained Understanding Expert ($E_{\mathrm{und}}$) and a structurally mirrored Generation Expert ($E_{\mathrm{gen}}$), coupled through shared global self-attention with hard modality routing. This design aligns the semantic latent space of the MLLM backbone with the geometric manifold, enabling direct transfer of multimodal priors without intermediate 2D representations. Results show that EVA01 achieves state-of-the-art native text-to-3D generation fidelity and unlocks robust long-context multi-turn geometric editing with identity preservation, a capability fundamentally inaccessible to stateless reconstruction pipelines. Our findings further offer architectural insights for integrating 2D foundation models with 3D tasks, informing the design of 3D-native multimodal systems. Project Page: https://www.seeles.ai/research/pages/EVA01

Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored. We introduce MAVEN, a multi-agent prompt refinement framework designed to improve cultural fidelity in both mono-cultural and cross-cultural T2V generation. MAVEN decomposes prompts into person, action, and location dimensions, handled by specialized agents operating in parallel or sequentially. To support systematic evaluation, we contribute a new benchmark of 243 culturally grounded prompts and 972 corresponding videos, spanning three cultures (Chinese, American, Romanian), three action categories, and both mono-cultural and cross-cultural scenarios. Evaluations combining CLIP-based metrics, VLM-as-judge assessments, and videoquality measures show that multi-agent refinement, particularly parallel specialization, significantly improves cultural relevance while preserving visual quality and temporal consistency. The dataset and code are available at https://github.com/AIM-SCU/MAVEN

Controllable multimodal generation is commonly formulated as an inference-time conditioning problem using prompts, guidance, or auxiliary modules. While effective, such approaches do not explicitly structure how semantic attributes evolve, which can lead to identity drift and inconsistent cross-modal behavior. We propose Controlla, a modular factorized-control framework that treats controllability as a property of structured latent geometry. Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport, encouraging attributes to follow graph-consistent trajectories while preserving reference identity. To evaluate this setting, we construct AffectHuman-43K, a leakage-aware multimodal benchmark for reference-grounded affective control, and introduce geometry-aware metrics for trajectory consistency and latent disentanglement. Experiments show consistent improvements in controllability, identity preservation, and cross-modal alignment, with additional analyses on graph sensitivity, extensibility, and robustness.

Agricultural landscape segmentation in the Global South is challenging as it is characterized by fragmented plots, high intra-class variance, and a scarcity of labeled training data. Recent advances in segmentation have been made by Multimodal Large Language Models (MLLMs). However, current approaches encounter critical context length bottlenecks and a domain alignment gap in understanding satellite features. We address these limitations through MAgSeg, a novel, decoder-free MLLM segmentation approach. MAgSeg is an architecturally efficient approach that enables standard MLLMs to perform segmentation of complex smallholder agricultural landscapes from high-resolution satellite imagery, without requiring auxiliary vision decoders. We introduce a novel instruction tuning data format designed to enable scalable fine-tuning and post-training on high resolution satellite imagery, which enables MAgSeg to learn from the global context of the image while generating text tokens for only a patch within the image. Extensive evaluations on datasets spanning three countries in the Global South demonstrate that MAgSeg significantly outperforms state-of-the-art MLLM baselines, offering a scalable solution to map smallholder agricultural environments.

Autoregressive next-token training offers a unified formulation for image generation and text understanding, but it also creates strong modality competition that destabilizes optimization and limits large-batch scaling. We show that first-order optimizers such as AdamW are vulnerable to cross-modality gradient heterogeneity, while second-order preconditioning, particularly SOAP, provides a more stable basis for multimodal alignment. Building on this insight, we propose \emph{ML-FOP-SOAP}, a second-order optimization framework with Multi-Level Variance Correction. Our Fisher-Orthogonal Projection suppresses variance-induced modality conflicts, reducing the trade-off between visual generation and textual understanding. To make this practical under large gradient accumulation, we introduce a hierarchical folding strategy that captures fine-grained variance with low micro-step overhead. Experiments on Janus and Emu3 show consistent gains across both modalities and stable training at batch size 8192. Compared with AdamW, our method improves sample efficiency by up to $1.4\times$ and accelerates wall-clock training by up to $1.5\times$, offering a robust optimizer for scaling multimodal foundation models.

Large vision-language models (LVLMs) have emerged as a powerful paradigm for multimodal intelligence, but their growing deployment also expands the attack surface of prompt injection. Despite this growing concern, existing attacks still suffer from a critical limitation: the injected prompt for one modality only steers the model's interpretation of that singular input. Alternatively, these attacks remain multimodal but fail to achieve cross-modal prompt perturbation. To bridge this gap, we introduce a novel cross-modal prompt injection attack CrossMPI, which can steer the model's interpretation of both textual and visual inputs via image-only prompt injection. Our design is underpinned by the following key breakthroughs. First, we turn the focus of the injected prompt perturbation optimization from the visual embedding space (typically with only $10^5$ parameters) to the model hidden state space (for multimodal information integration and with $10^7$ parameters). Then, two strategies are adopted to mitigate the optimization challenges posed by the larger parameter space. To constrain the optimized model parameter space, we introduce a layer selection strategy that identifies the layers most critical to multimodal integration. Interestingly, deviating from the past experience, our analysis reveals that the optimal layers for LVLM prompt perturbation reside in the middle of the model rather than the last. To constrain the image perturbation space, we propose a new distance-decremental perturbation budget assignment strategy that allocates budgets decrementally as the pixel distance to semantic-critical regions increases. Extensive experiments across multiple LVLMs and datasets show that our method significantly outperforms baseline approaches.

This paper introduces a dataset of interlinked multimodal political communications from the Russian government, addressing persistent deficiencies in the availability of social text- and image-based data for authoritarian politics contexts. The dataset comprises two large corpora of official speeches delivered by senior actors within the Kremlin and the Russian Ministry of Foreign Affairs over multiple decades. For each speech, we provide Russian- and English-language texts, associated images and captions where available, and harmonized metadata including (e.g.) dates, speakers, (geo)locations, and official government content tags. Unique identifiers link images to speeches and align Russian and English versions of the same communication texts. We further augment these linked datasets with validated topical annotations for both speech texts and speech images, which are generated via transformer-based multimodal topic modeling and refined by a Russian politics expert. The resulting data resources support multimodal, multilingual, temporal, and/or spatial analyses of (authoritarian) political communication and offer a valuable testbed for social science research and large language model (LLM) applications in political domains.

We present ForMaT (Format-Preserving Multilingual Translation), a parallel corpus of 3,956 PDFs across 15 language pairs that preserves original layout metadata proposed for multimodal machine translation. To ensure structural diversity in the dataset, we employ K-Medoids sampling over 45 geometric features, capturing complex elements like nested tables and formulas to focus only on visually diverse PDF documents. Our evaluation reveals that current MT systems struggle with spatial grounding and geometric synchronization, often losing the link between text and its visual context. ForMaT provides a benchmark for developing layout-aware translation models that integrate visual and textual context for high-fidelity document reconstruction.

The long-standing goal of multimodal AI is to build unified models in which visual understanding and visual generation mutually enhance one another. Despite recent works such as BAGEL, BLIP3o achieves remarkable progress; In practice, however, this unification remains one-directional: understanding routinely guides generation, yet how and why generation can support understanding is rarely investigated. We revisit this asymmetry and propose Generation-to-Understanding (G2U) synergy, where visual generation becomes an explicit intermediate reasoning step. Our framework enables a model to perform controlled generative acts, such as detail enhancement, context expansion or structural visualisation, to produce self-generated visual thoughts, which are then fed back into the model to refine perception without retraining or external tools. Through a comprehensive evaluation on twelve benchmarks, this reversed information flow consistently improves multimodal understanding. We show that generative fidelity bounds perceptual gain and that distinct families of edit prompts govern transfer efficiency. We further analyse whether models can decide what to imagine. While they can produce plausible edits, these self-generated visual thoughts lack stable task alignment, revealing that current large multimodal models fall short of true self-reflection. This work exposes a missing mechanism in unified cognition and suggests that imagination is not the end of understanding but its beginning.

Multimodal large language models (MLLMs) can produce fluent artwork emotion explanations, but they often suffer from attribute flooding: they enumerate many visible formal attributes without identifying which cues actually support the affective judgment. We therefore formulate artwork emotion understanding as Attribute-Grounded Selective Reasoning (AGSR), where predefined formal attributes serve as evidence units and only emotionally operative attributes should enter the final interpretation. To make this problem measurable, we extend EmoArt, originally introduced at ACM MM 2025 as a 132,664-artwork resource with content, formal-attribute, valence-arousal, and emotion annotations, by adding a 1,400-artwork human salience extension annotated by 15 art-trained annotators. This extension provides instance-level supervision for distinguishing attributes that are merely present from those that are emotionally salient. We further propose FAB-G (Formal-Attribute Bottleneck-Guided reasoning), a supervised multi-agent framework that first predicts attribute-level salience and then constrains downstream emotional analysis to the retained cues. Experiments show that FAB-G yields consistent gains in emotion, arousal, and valence prediction, achieves stronger agreement with human-marked salient attributes under Dice and Tversky metrics, and produces substantially more compact final explanations than prompting-based baselines. Cross-dataset evaluation further suggests that attribute-grounded salience selection transfers beyond the source distribution of EmoArt, while also revealing attribute-specific boundary cases. The dataset and project page are available at https://zhiliangzhang.github.io/EmoArt-130k/

Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes and edges encode corpus structure, provide a natural setting for refining frozen vision-language embeddings. This refinement is challenging: visual, textual, and cross-modal relations often induce different neighborhood geometries, while unrestricted graph propagation can quickly over-smooth retrieval representations. Effectively leveraging graph context therefore requires simultaneously breaking modality-specific topological barriers, controlling the smoothing regime, and preserving informative smoothing before semantic boundaries collapse. We propose Graph-Optimized Multimodal Alignment (GOMA), a structure-driven post-alignment framework that views frozen multimodal embeddings as graph signals and addresses these requirements through a unified retrieval-oriented design. GOMA decouples three key design choices: where messages should flow, how multimodal evidence should propagate, and which smoothing depth should be retained. Concretely, it learns modality-aware propagation operators, performs finite-step coupled smoothing without diagonal cross-modal shortcuts, and adaptively reads out node-specific smoothing trajectories to preserve useful smoothing before collapse. All experiments follow a transductive MAG retrieval protocol where the graph serves only as unlabeled context and diagonal self-pair edges are removed. On seven MAG benchmarks, GOMA achieves state-of-the-art or tied state-of-the-art retrieval and remains substantially more stable than the strongest graph competitor, demonstrating that MAG structure can serve as an effective post-encoder for frozen multimodal embeddings.

Medical referring image segmentation (MRIS) requires pixel-level masks aligned with textual descriptions of anatomical locations, making annotation costly in low-label regimes. Semi-supervised learning (SSL) can mitigate this burden by leveraging unlabeled data, but its success hinges on maintaining reliable image-text alignment under perturbations. Most existing SSL-based referred segmentation methods use either independent or simplistic multi-modal perturbations (e.g., left-right flips), without fully addressing cross-modal alignment under strong augmentation, while CutMix, highly effective in single-modal SSL, remains underexplored in multi-modal settings due to its tendency to disrupt image-text coherence. We propose Semi-MedRef, a teacher-student SSL framework designed to explicitly maintain consistency between medical images and positional language through three alignment-preserving components: T-PatchMix, a cross-modal CutMix-style augmentation that synchronizes patch mixing with referring expressions via position-constrained and probability-driven rules; PosAug, a position-aware text augmentation that masks or fuzzes anatomical phrases; and ITCL, a position-guided image-text contrastive learning module, which leverages positional pseudo-labels to construct soft anatomical positives and strengthen medically grounded cross-modal alignment. Experiments on QaTa-COV19 and MosMedData+ demonstrate that Semi-MedRef consistently outperforms both fully supervised and semi-supervised baselines across all label regimes.

Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use evidence distributed across independently originated sources. We argue that source-distributed memory composition is an important and under-examined bottleneck in multimodal agent memory, especially when relevant evidence is fragmented across heterogeneous artifacts such as conversations, profiles, screenshots, tables, images, and documents. To address this gap, we introduce Source-distributed Multimodal Memory Benchmark(SMMBench), which measures whether agents can retrieve, align, and compose multimodal evidence scattered across multiple sources rather than reason within a single curated context. SMMBench evaluates four core capabilities: (1) cross-source multimodal reasoning; (2) conflict resolution; (3) preference reasoning; (4) memory-grounded action prediction. The benchmark contains 1877 samples grounded in 264 sources. Experiments on representative memory-style and retrieval-based baselines show that current systems still struggle on these capabilities, positioning source-distributed multimodal memory as an important and still under-evaluated challenge for multimodal agents. Our data are available at https://huggingface.co/datasets/HuacanChai/SMMBench.

Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations, while overlooking the generation quality after unlearning. This can easily lead to hallucinated or rigid responses, thereby affecting the usability and safety of the unlearned model. To address this issue, we propose ASRU, a controllable multimodal unlearning framework that incorporates generation quality as a core evaluation objective. ASRU first induces initial refusal behavior through activation redirection, and then optimizes fine-grained refusal boundaries using a customized reward function, thereby achieving a better trade-off between target knowledge unlearning and model utility. Experiments on Qwen3-VL show that ASRU significantly improves unlearning effectiveness (+24.6%) on average and generation quality (5.8X) on average while effectively preserving model utility, using only a small amount of retained supervision data.

Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lack robust control over basic visual operations. We study \textit{line tracing}, where a model must follow a selected visual path through successive local continuations. To isolate this ability, we design controlled tracing tasks that introduce nearby competitors while reducing semantic and topological ambiguity such as crossings and overlaps. Across these tasks, even state-of-the-art VLMs frequently lose the target path and switch to nearby alternatives, especially when those alternatives look locally similar to the target. Behavioral interventions and internal analyses indicate that these failures arise from local competition: nearby similar distractors pull the model away from the true continuation. Standard remedies do not remove this bottleneck: model-size scaling provides only limited gains, reasoning partially compensates through costly substitute strategies, and explicit tracing instructions fail to recover stable path following. Finally, tests on tangled-cable scenes and metro maps with richer visual complexity show that the same path-switching failure persists beyond our controlled settings.

Recent diffusion-based methods for material transfer rely on image fine-tuning or complex architectures with assistive networks, but face challenges including text dependency, extra computational costs, and feature misalignment. To address these limitations, we propose MaTe, a streamlined diffusion framework that eliminates textual guidance and reference networks. MaTe integrates input images at the token level, enabling unified processing via multi-modal attention in a shared latent space. This design removes the need for additional adapters, ControlNet, inversion sampling, or model fine-tuning. Extensive experiments demonstrate that MaTe achieves high-quality material generation under a zero-shot, training-free paradigm. It outperforms state-of-the-art methods in both visual quality and efficiency while preserving precise detail alignment, significantly simplifying inference prerequisites.

Accurate peak detection across diverse cardiac physiological signals, including the Electrocardiogram (ECG), Photoplethysmogram (PPG), Ballistocardiogram (BCG), and Bodyseismography (BSG), is fundamental for cardiovascular monitoring but is often hindered by artifacts and signal variability. Conventional algorithms are typically engineered with expert knowledge for a single signal modality, limiting their generalizability. Conversely, deep learning-based methods often lack interpretability, limiting transparency for expert verification and hindering expert-computer interaction. To address these limitations, we introduce Peak-Detector, a novel framework that leverages instruction-tuned Large Language Models (LLMs) for robust, cross-modal, and explainable peak detection. A core innovation of our framework is a "peak-representation" technique that transforms time-series data into a condensed format, preserving critical event information while significantly reducing signal length. This representation provides a crucial inductive bias, guiding the LLM to reason over physiologically meaningful events rather than raw, noisy data. The model is optimized through a two-stage process: supervised fine-tuning (SFT) followed by reinforcement learning (RL) with a multi-objective reward function. The model's self-explanation capabilities are cultivated by fine-tuning on a custom-built Peak-Explanation dataset. Across four modalities-ECG, PPG, BCG, and BSG-spanning seven datasets (six public benchmarks plus one real-world cohort), Peak-Detector demonstrates strong cross-modal performance, achieving best or tied-best detection under clinically relevant temporal tolerance. Beyond accuracy, the generated rationales surface failure modes and support verification and error analysis.

GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability in understanding and executing user instructions. However, accurately grounding instruction-relevant elements from high-resolution screenshots cluttered with irrelevant UI components remains challenging for existing approaches. Inspired by how humans dynamically adjust their perceptual scope to locate task-related regions on complex screens, we propose DRS-GUI, a training-free dynamic region search framework for GUI grounding that can be seamlessly integrated into existing MLLMs. DRS-GUI introduces a lightweight UI Perceptor that performs three human-like perceptual actions (Focus, Shift, and Scatter) to progressively explore the interface and generate region proposals. To dynamically schedule these actions, we further design an Action Planner based on Monte Carlo Tree Search (MCTS). A region quality reward is employed to evaluate and select the highly instruction-relevant region, efficiently pruning redundant UI elements. Experiments demonstrate that DRS-GUI yields a 14% improvement on ScreenSpot-Pro for general and GUI-specific MLLMs (Qwen2.5-VL-7B and UGround-V1-7B), significantly enhancing grounding performance and generalization.

Cross-modal hashing enables efficient retrieval by encoding images and text into compact binary codes. State-of-the-art methods rely on semantic similarity graphs derived from user interactions for supervision, yet these graphs encode sensitive behavioral patterns vulnerable to link reconstruction attacks. Existing privacy-preserving approaches fail on graph-structured data: Differentially Private SGD destroys relational motifs by treating samples independently, while graph synthesis methods suffer from unbounded local sensitivity in scale-free networks, hub nodes cause single-edge modifications to alter triangle counts by $\mathcal{O}(N)$, necessitating prohibitive noise injection. We term this phenomenon Hubness Explosion. We propose DMP-MH, a Sanitize-then-Distill framework that decouples privacy from representation learning. Our approach first bounds sensitivity by deterministically clipping node degrees, capping the $L_2$-sensitivity of triangle motifs independently of dataset size. A sanitized synthetic graph is then generated via Noisy Mirror Descent under $(ε,δ)$-Edge Differential Privacy. Finally, dual-stream hashing networks distill this topology using a holistic structural loss that enforces cross-modal alignment. Evaluated on MIRFlickr-25K and NUS-WIDE under a strict inductive protocol, DMP-MH outperforms private baselines by up to 11.4 mAP points while retaining up to 92.5% of non-private performance.

Most Vision Language Models (VLMs) directly map outputs from ViT encoders to the LLM via a lightweight projector. While effective, recent analysis suggests this architecture suffers from an alignment challenge: visual features remain distant from the text space in the initial layers of the LLM, forcing the model to waste critical depth~\cite{zhang-etal-2024-investigating,artzy-schwartz-2024-attend} on superficial modality alignment rather than deep understanding and complex reasoning. In this work, we propose Deep Pre-Alignment (DPA), a novel architecture that replaces the standard ViT encoder with a small VLM as perceiver, ensuring visual features are deeply aligned with the text space of the target large language model. Comprehensive experiments demonstrate the effectiveness of DPA. On the 4B parameter scale, DPA outperforms baselines by 1.9 points across 8 multimodal benchmarks, with gains widening to 3.0 points at the 32B scale. Moreover, by offloading alignment to the perceiver, DPA achieves a 32.9% reduction in language capability forgetting over 3 text benchmarks. We further demonstrate that these gains are consistent across different LLM families including Qwen3 and LLaMA 3.2, highlighting the generality of our approach. Beyond performance, DPA also offers a seamless upgrade path for current VLM development, requiring only a modular replacement for the visual encoder with marginal computation overhead.

Reconstructing precise clinical timelines is essential for modeling patient trajectories and forecasting risk in complex, heterogeneous conditions like sepsis. While unstructured clinical narratives offer semantically rich and contextually complete descriptions of a patient's course, they often lack temporal precision and contain ambiguous event timing. Conversely, structured electronic health record (EHR) data provides precise temporal anchors but misses a substantial portion of clinically meaningful events. We introduce a retrieval-augmented multimodal alignment framework that bridges this gap to improve the temporal precision of absolute clinical timelines extracted from text. Our approach formulates timeline reconstruction as a graph-based multistep process: it first extracts central anchor events from narratives to build an initial temporal scaffold, places non-central events relative to this backbone, and then calibrates the timeline using retrieved structured EHR rows as external temporal evidence. Evaluated using instruction-tuned large language models on the i2m4 benchmark spanning MIMIC-III and MIMIC-IV, our multimodal pipeline consistently improves absolute timestamp accuracy (AULTC) and improves temporal concordance across nearly all evaluated models over unimodal text-only reconstruction, without compromising event match rates. Furthermore, our empirical gap analysis reveals that 34.8% of text-derived events are entirely absent from tabular records, demonstrating that aligning these modalities can produce a more temporally faithful and clinically informative reconstruction of patient trajectories than either source alone.

Multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities (entire images or scenes), creating a mismatch with fine-grained user queries and making failures unverifiable. We introduce GranuVistaVQA, a multimodal benchmark featuring real-world landmarks with element-level annotations across multiple viewpoints, capturing the partial observation challenge where individual images contain only subsets of entities. We further propose GranuRAG, a multi-granularity framework that treats visual elements as first-class retrieval units through three stages: element-level detection and classification, multi-granularity cross-modal alignment for evidence retrieval, and attribution-constrained generation. By grounding retrieval at the element level rather than relying on implicit attention, our approach enables transparent error diagnosis. Experiments demonstrate that GranuRAG achieves up to 29.2% improvement over six strong baselines for this task.

Large vision-language models (LVLMs) have achieved remarkable performance across diverse multimodal tasks, yet they continue to suffer from hallucinations, generating content that is inconsistent with the visual input. Prior work DHCP (Detecting Hallucinations by Cross-modal Attention Pattern) has explored hallucination detection from the perspective of cross-modal attention, but does not address hallucination mitigation. In this paper, we propose MHSA (Mitigating Hallucinations via Steered Attention), a lightweight framework that mitigates hallucinations by learning to correct cross-modal attention patterns in LVLMs. MHSA trains a simple three-layer MLP generator to produce corrected attention, guided by supervisory signals from the DHCP discriminator and the LVLM itself. During inference, MHSA mitigates both discriminative and generative hallucinations across various datasets and LVLMs by simply replacing the original cross-modal attention with the corrected one, without modifying any LVLM parameters. By extending cross-modal attention mechanisms from hallucination detection to hallucination mitigation, MHSA offers a novel perspective on hallucination research in LVLMs and helps enhance their reliability.

Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet existing methods face inherent limitations: architecture-based approaches incur additional computational overhead and often generalize poorly to new tasks, rehearsal-based methods rely on storing historical data, raising privacy and storage concerns, and conventional regularization-based strategies alone are insufficient to fully prevent parameter interference. We propose Octopus, a two-stage continual learning framework based on History-Free Gradient Orthogonalization (HiFGO), which enforces gradient-level orthogonality without historical task data. Our proposed two-stage finetuning strategy decouples task adaptation from regularization, achieving a principled balance between plasticity and stability. Experiments on UCIT show that Octopus establishes state-of-the-art performance, surpassing prior SOTA by 2.14% and 6.82% in terms of Avg and Last.

Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA) remains largely unexplored. VP-QA presents unique challenges where users query next-step actions by uploading images for intermediate states of complex procedures. To systematically evaluate VLMs on this practical task, we propose ProcedureVQA, a novel multimodal benchmark specifically designed for visual procedural reasoning. Through comprehensive analysis, we identify two critical limitations in current VLMs: inadequate cross-modal retrieval of structured procedures given visual states, and misalignment between image sequence granularity and textual step decomposition. To address these issues, we present Chain-of-Procedure (CoP), a hierarchical reasoning framework that first retrieves relevant instructions using visual cues, then performs step refinement through semantic decomposition, and finally generates the next step. Experiments across six VLMs demonstrate CoP's effectiveness, achieving up to 13% absolute improvement over standard baselines.

Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and memory-augmented agents. However, no existing benchmark conducts a systematic comparison of the two on questions that genuinely require multimodal evidence. To close this gap, we introduce MEMLENS, a comprehensive benchmark for memory in multimodal multi-session conversations, comprising 789 questions across five memory abilities (information extraction, multi-session reasoning, temporal reasoning, knowledge update, and answer refusal) at four standard context lengths (32K-256K tokens) under a cross-modal token-counting scheme. An image-ablation study confirms that solving MEMLENS requires visual evidence: removing evidence images drops two frontier LVLMs below 2% accuracy on the 80.4% of questions whose evidence includes images. Evaluating 27 LVLMs and 7 memory-augmented agents, we find that long-context LVLMs achieve high short-context accuracy through direct visual grounding but degrade as conversations grow, whereas memory agents are length-stable but lose visual fidelity under storage-time compression. Multi-session reasoning caps most systems below 30%, and neither approach alone solves the task. These results motivate hybrid architectures that combine long-context attention with structured multimodal retrieval. Our code is available at https://github.com/xrenaf/MEMLENS.

Automatic recognition of affective state from wearable physiology has clear societal impact for public health, preventive care, and stress-aware interventions, but real deployments require robustness to non-stationary dynamics, artefacts, and missing sensors. We study this problem on WESAD, using baseline, stress, and amusement conditions, where common fixed-basis spectral features such as FFT bandpower and Welch PSD can oversmooth short-lived discriminative patterns. We propose a non-stationary pipeline that combines Fourier-Bessel Series Expansion (FBSE) with EWT data-driven spectral segmentation to extract mode-wise transient descriptors. For multimodal integration, we adopt decision-level aggregation over per-modality predictors and weight each modality by predictive uncertainty and modality reliability. Results on WESAD, using 15 subjects and ECG, EDA, BVP, EMG, and ACC signals across three classes, indicate that decision-level aggregation is approximately 84 percent of the time at least as good as feature-level aggregation, and approximately 48 percent of the time strictly better, suggesting improved robustness under heterogeneous and partially reliable sensing.

Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge into precise pixel-level manipulation. This gap results in two bottlenecks in anything-to-image task (X2I): the attention entanglement bottleneck, where blind planning struggles with complex prompts, and the visual refinement bottleneck, where unstructured feedback fails to correct imperfections efficiently. In this paper, we propose a novel framework that empowers unified models to autonomously switch between generation strategies based on instruction complexity and model capability. To achieve this, we construct a hierarchical data pipeline that constructs execution paths across three adaptive modes: direct generation for simple cases, self-reflection for quality refinement, and multi-step planning for decomposing complex scenarios. Building on this pipeline, we contribute a high-quality dataset with over 50,000 samples and implement a two-stage training strategy comprising SFT and RL. Specifically, we design step-wise reasoning rewards to ensure logical consistency and intra-group complexity penalty to prevent redundant computational overhead. Extensive experiments demonstrate that our method outperforms existing baselines on X2I, achieving superior generation fidelity among simple-to-complex instructions. The code is released at https://github.com/WeChatCV/Interleaved_Visual_Reasoner.

Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose StyleTextGen, a novel framework that learns to perceive and replicate visual text styles across different languages and writing systems. Our approach features three key contributions: First, we introduce a dual-branch style encoder dedicated to style modeling, yielding robust multilingual text style representations in complex real-world scenes. Second, we design a text style consistency loss that enhances style coherence and improves overall visual quality. Third, we develop a mask-guided inference strategy that ensures precise style alignment between generated and reference text. To facilitate systematic evaluation, we construct StyleText-CE, a bilingual scene text style benchmark covering both monolingual and cross-lingual settings. Extensive experiments demonstrate that StyleTextGen significantly outperforms existing methods in style consistency and cross-lingual generalization, establishing new state-of-the-art performance in multilingual style-conditioned text generation.

This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language models (MLLMs) to predict the emotions evoked by images. Recent user studies report an unintuitive finding: humans may prefer the predictions of MLLMs over the labels in existing datasets. We argue that this phenomenon stems from the suboptimal annotation scheme used in existing datasets, where each annotator is shown a single candidate emotion for each image and judges whether it is evoked or not. This approach is clearly limited because a single image can evoke multiple emotions with varying intensities. As a result, evaluations based on these datasets may underestimate the capabilities of MLLMs, yet an appropriate benchmark for evaluating such models remains lacking. To address this issue, we introduce a new multi-label benchmark dataset for visual emotion analysis toward MLLMs evaluation. We hire $20$ annotators per image and ask them to select all emotions they feel from an image. Then, we aggregate the votes across all annotators, providing a more reliable and representative dataset labeled with a distribution of emotions. The resulting dataset contains $10,344$ images with $236,998$ valid votes across eight emotions. Based on this benchmark dataset, we evaluate several recent models, including Qwen3-VL, OpenAI's GPT, Gemini, and Claude. We assess model performance on both dominant emotion prediction and emotion distribution prediction. Our results demonstrate the progress achieved by recent MLLMs while also indicating that substantial room for improvement remains. Furthermore, our experiments with LLM-as-a-judge show that the method does not consistently improve MLLMs' performance, indicating its limitations for the subjective task of visual emotion analysis.

RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional processes. As a result, consistency among VIS, IR, and Label in spatial structure, semantic content, and cross-modal details cannot be reliably maintained. To address this issue, we propose UniTriGen, a unified triplet generation framework that directly generates spatially aligned, semantically consistent, and modality complementary VIS-IR-Label triplets under the guidance of text prompts. UniTriGen first introduces a unified triplet generation mechanism, where VIS, IR, and Label are jointly encoded into a shared latent space and modeled with a diffusion process to enforce global cross-modal consistency. Lightweight modality-specific residual adapters are further integrated into this mechanism to accommodate modality-specific imaging characteristics and output formats. To mitigate generation bias caused by imbalanced scene and class distributions in limited paired triplets, UniTriGen also employs a scene-balanced and class-aware few-shot sampling strategy, which induces a more balanced sampling distribution and enhances the scene and class diversity of generated triplets. Experiments show that UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models.

Omni-modal large language models have demonstrated remarkable potential in holistic multimodal understanding; however, the token explosion caused by high-resolution audio and video inputs remains a critical bottleneck for real-time applications and long-form reasoning. Existing omni-modal token compression methods typically prune tokens at the input embedding level, relying on audio-video similarity or temporal co-occurrence as proxies for semantic relevance. In practice, such assumptions are often unreliable. To address this limitation, we propose OmniDrop, a training-free, layer-wise token pruning framework that progressively prunes audiovisual tokens within the LLM decoder layers rather than at the input-level, allowing early layers to preserve sufficient omni-modal information fusion before aggressively removing tokens in deeper layers. We further utilize text queries as guidance for modality-agnostic and task-adaptive token pruning. We also introduce a temporal diversity score that encourages balanced token survival to preserve global temporal context. Experimental results across various audiovisual benchmarks demonstrate that OmniDrop outperforms all baselines by up to 3.58 points while reducing prefill latency by up to 40% and memory usage by up to 14.7%.

Multimodal large language models (MLLMs) have emerged as a powerful backbone for multimodal embeddings. Recent methods introduce chain-of-thought (CoT) reasoning into the embedding pipeline to improve retrieval quality, but remain costly in both model size and inference cost. They typically employ separate reasoner and embedder with substantial parameter overhead, and generate CoT indiscriminately for every input. However, we observe that for simple inputs, discriminative embeddings already perform well, and redundant reasoning can even mislead the model, degrading performance. To address these limitations, we propose Think When Needed (TWN), a unified multimodal embedding framework with adaptive reasoning. TWN introduces a dual-LoRA architecture that attaches reasoning and embedding adapters to a shared frozen backbone, detaching gradients at their interface to mitigate gradient conflicts introduced by joint optimization while keeping parameters close to a single model. Building on this, an adaptive think mechanism uses a self-supervised routing gate to decide per input whether to generate CoT, skipping unnecessary reasoning to reduce inference overhead and even improve retrieval quality. We further explore embedding-guided RL to optimize CoT quality beyond supervised training. On the 78 tasks of MMEB-V2, TWN achieves state-of-the-art embedding quality while being substantially more efficient than existing generative methods, requiring only 3-5% additional parameters relative to the backbone and up to 50% fewer reasoning tokens compared to the full generative mode.

Large-scale pretraining on Earth observation imagery has yielded powerful representations of the natural and built environment. However, most existing geospatial foundation models do not directly model the structured socioeconomic covariates typically stored in tabular form. This modality gap limits their ability to capture the complete total environment, which is critical for reasoning about complex environmental, social, and health-related outcomes. In this work, we propose GeoViSTA (Geospatial Vision-Tabular Transformer), a vision-tabular architecture that learns unified geospatial embeddings from co-registered gridded imagery and tabular data. GeoViSTA utilizes bilateral cross-attention to exchange spatial and semantic information across modalities, guided by a geography-aware attention mechanism that aligns continuous image patches with irregular census-tract tokens. We train GeoViSTA with a self-supervised joint masked-autoencoding objective, forcing it to recover missing image patches and tabular rows using local spatial context and cross-modal cues. Empirically, GeoViSTA's unified embeddings improve linear probing performance on high-impact downstream tasks, outperforming baselines in predicting disease-specific mortality and fire hazard frequency across held-out regions. These results demonstrate that jointly modeling the physical environment alongside structured socioeconomic context yields highly transferable representations for holistic geospatial inference.

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced since a single image often contains multiple entangled concepts, including both target concepts to be forgotten and contextual information that should be preserved. In this paper, we propose an interpretable concept-level unlearning framework for VLMs, which constructs a compact task-specific concept vocabulary from the forgetting set using a multimodal large language model. In addition to modality alignment, visual representations are decomposed into sparse, nonnegative combinations of semantic concepts, providing an explicit interface for fine-grained knowledge manipulation. Based on this decomposition, our method formulates unlearning as concept-level optimization, where target concepts are selectively suppressed while intra-instance non-target semantics and global cross-modal knowledge are preserved. Extensive experiments across both in-domain and out-of-domain forgetting settings demonstrate that our method enables more comprehensive target forgetting, better preserves non-target knowledge within the same image, and maintains competitive model utility compared with existing VLM unlearning methods.

Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-to-image generation, yet they frequently suffer from concept omission, where specified objects or attributes fail to emerge in the generated image. By performing linear probing on text tokens, we demonstrate that text embeddings can distinguish a characteristic `omission signal' representing the absence of target concepts. Leveraging this insight, we propose Omission Signal Intervention (OSI), which amplifies the omission signal to actively catalyze the generation of missing concepts. Comprehensive experiments on FLUX.1-Dev and SD3.5-Medium demonstrate that OSI significantly alleviates concept omission even in extreme scenarios.

Large language models (LLMs) often expose useful signals of self-monitoring: before solving a problem, they can estimate whether they are likely to succeed, and after solving it, they can judge whether their answer is likely to be correct. However, these signals are typically measured or elicited in isolation, rather than used to control inference. In this work, we ask whether LLMs possess latent metacognitive ability that can be turned into effective test-time control. Inspired by the Nelson--Narens theory from cognitive psychology, we propose a metacognitive harness that separates monitoring from reasoning. For each problem, the model first reports a pre-solve feeling-of-knowing (FOK) signal; after each solve attempt, it reports a post-solve judgment-of-learning (JOL) signal. Rather than treating these signals as passive confidence estimates, the harness turns them into an explicit control interface for reasoning: it decides when to trust the current solution, when to retry with compact metacognitive feedback, and when to pass multiple attempts to a final aggregator. Across text, code, and multimodal reasoning benchmarks, our harness substantially improves a fixed Claude Sonnet-4.6 base model without parameter updates or benchmark-specific fine-tuning. On the evaluated public benchmark snapshots, it raises pooled accuracy from 48.3 to 56.9 and exceeds the strongest listed leaderboard entries on the three primary evaluation settings: HLE-Verified, LiveCodeBench v6, and R-Bench-V. These results suggest that strong LLMs may already possess useful metacognitive ability, but require an explicit control harness to act on it during reasoning.

Multimodal physiological data powers clinical AI systems from intensive care units to wearable devices, but sensors routinely fail in practice. Two failure modes are common: modality missing, where an entire channel is absent, and within-modality missing, where a contiguous time segment is lost. No existing benchmark evaluates multiple fusion architectures under both failure modes at controlled severity levels across diverse clinical datasets. We present MuteBench, a benchmark covering 9 datasets from 7 clinical domains, 6 fusion architectures, and 2 missing-data modes over 125,000 samples. Through this benchmark, we find that architecture family is the strongest predictor of robustness, outweighing parameter count. Channel-independent models tolerate modality missing well but can be sensitive to within-modality missing, especially on short sequences. Curriculum modality dropout protects reliably only up to the maximum dropout rate used in training. We also find that channel count, sequence length, and modality alignment jointly determine which failure mode poses the greater threat. Finally, a PTB-XL case study suggests that diffusion-based imputation can improve downstream classification under within-modality missing, with the largest gains for models whose expert routing is most sensitive to corrupted inputs, though broader validation across datasets remains an open direction. MuteBench provides practitioners with concrete guidance for both selecting existing architectures and informing the design of future robust multimodal fusion methods.

Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or agentic workflows. However, these approaches are often limited by static textual reasoning or complicated by the significant compute and engineering burden of external agentic complexity. Worse, this heavy investment does not yield proportional gains, often witnessing a "seesaw effect" on perception and reasoning. This motivates a fundamental rethinking of the true bottleneck. In this paper, we argue that the root cause of this trade-off is an ambiguity in modality credit assignment: when a VLM fails, is it due to flawed perception ("bad seeing") or flawed logic ("bad thinking")? To resolve this, we introduce a reinforcement learning framework that improves perception-reasoning synergy by reliably rewarding the perception fidelity. We explicitly decompose the generation process into interleaved perception and reasoning steps. This decoupling enables targeted supervision on perception. Crucially, we introduce Perception Verification (PV), leveraging a "blindfolded reasoning" proxy to reward perceptual fidelity independently of reasoning outcomes. Furthermore, to scale training across free-form VL tasks, we propose Structured Verbal Verification, which replaces high-variance LLM judging with structured algorithmic execution. These techniques are integrated into a Modality-Aware Credit Assignment (MoCA) mechanism, which routes rewards to the specific source of error -- either bad seeing or bad thinking -- enabling a single VLM to achieve simultaneous performance gains across a wide task spectrum.

Vision-Language Models (VLMs) have achieved strong performance on general multimodal reasoning, yet remain challenged in integrating nonlocal visual information to support semantically underdetermined visual reasoning. We describe this challenge as Fragmented Visual Reasoning. To this end, we propose Credit Assignment for Visual Evidence (CAVE), a structured process-reward method based on GRPO for interleaved visual reasoning. Specifically, CAVE evaluates the contribution of intermediate steps at the action level via three complementary reasoning process signals: belief update, evidence acquisition, and adaptive focus control, thereby guiding the model to optimize each reasoning action and learn more reliable visual reasoning strategies. Meanwhile, we construct TRACER-Bench, which covers four nonlocal and semantically confusable reasoning dimensions and provides key intermediate evidence to supervise reasoning paths. Experiments demonstrate that CAVE substantially improves performance on tasks requiring fragmented visual evidence integration, covering both public benchmarks and our newly introduced TRACER-Bench, while retaining competitive performance on general multimodal evaluations. Further analyses reveal that CAVE effectively improves the visual reasoning capacity and exhibits stronger robustness under longer-range and deeper cross-region dependencies.

When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perception or in action? Recent omnimodal models are positioned as perception-grounded agents that jointly process video, audio, and text, yet a basic form of grounding remains untested: catching a textual claim that conflicts with the model's own sensory input. We introduce IMAVB, a curated 500-clip benchmark of long-form movies with a 2x2 design crossing target modality (vision, audio) and premise condition (standard, misleading), which lets us measure conflict detection separately from ordinary multimodal comprehension. Across eight open-source omnimodal LLMs and Gemini 3.1 Pro, we document a Representation-Action Gap: hidden states reliably encode premise-perception mismatches even when the same models almost never reject the false claim in their outputs. Behaviorally, models fall into two failure modes: under-rejection, in which they answer misleading questions as if the false premise were true; and over-rejection, in which they reject more often but also reject standard questions, sacrificing ordinary comprehension accuracy. The gap is modality-asymmetric (audio grounding underperforms vision) and prompt-resistant across seven variants. As an initial diagnostic intervention, a probe-guided logit adjustment (PGLA) re-injects the encoded mismatch signal into decoding and consistently improves rejection behavior. Together, these results suggest the bottleneck for omnimodal grounding lies in translation, not perception.

Diagnosing esophageal motility disorders pose significant challenges due to the complexity of high-resolution impedance manometry (HRIM) data and variability in clinical interpretation. This work explores the feasibility of a multimodal Machine Learning (ML)-based classification approach that combines HRIM recordings with patient-specific information and incorporates a graph-based modeling of esophageal physiology. We analyze HRIM recordings with corresponding patient information from 104 patients with esophageal motility disorders. Patient data includes demographic, clinical, and symptom information extracted from structured questionnaires and free-text notes using keyword detection and large language model-based processing. HRIM data is represented as spatio-temporal graphs, where nodes correspond to pressure values along the esophagus and edges encode spatial adjacency and impedance dynamics. A graph neural network (GNN) is applied to learn physiologically meaningful representations, which are fused with patient embeddings for multi-category, multi-class classification of swallow events. The impact of patient features and graph-based modeling is evaluated by ablation studies and comparison to vision-based classifier baselines. The proposed multimodal approach indicates improvements over models that rely solely on HRIM-derived features across all classification categories. Additionally, the graph-based modeling provides gains compared to vision-based baselines. Our experiments systematically assess the complementary contribution of multiple modalities, as well as demonstrate the feasibility of our proposed graph-based approach. Our initial findings demonstrate that integrating patient-level data with graph-based representations of HRIM signals appears to be a promising direction for more accurate classification of esophageal motility disorders.

Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion, and complex typography. We present an OCR-aware multilingual multimodal training framework that combines (i) large-scale synthetic OCR-to-translation data generation, (ii) OCR-aware supervised fine-tuning (SFT) with LoRA adaptation, and (iii) structured visual chain-of-thought (CoT) prompting for reasoning under uncertain visual conditions. Using a LLaMA-based multimodal architecture, the proposed framework substantially improves OCR completeness, multilingual translation accuracy, and robustness under degraded visual conditions. Experimental results on multilingual receipts, menus, posters, signs, handwritten text, and document images demonstrate significantly improved visual-text grounding compared with the baseline model. In particular, the proposed OCR-aware post-training framework improves extraction of small, blurred, spatially scattered, and partially occluded text while reducing reliance on language priors under uncertain OCR conditions. Qualitative comparisons with frontier multimodal systems, including GPT-5-class and Gemini-family models, further suggest improved OCR grounding and reduced hallucination under noisy and visually ambiguous OCR scenarios. Overall, the results indicate that data-centric OCR-aware multimodal post-training provides an effective and scalable direction for improving multilingual OCR and OCR-based visual question answering systems.

Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines. For visual agents, however, procedural knowledge is inherently multimodal: reuse depends not only on what operation to perform, but also on recognizing the relevant state, interpreting visual evidence of progress or failure, and deciding what to do next. We formalize this requirement as multimodal procedural knowledge and address three practical challenges: (I) what a multimodal skill package should contain; (II) where such packages can be derived from public interaction experience; and (III) how agents can consult multimodal evidence at inference time without excessive image context or over-anchoring to reference screenshots. We introduce MMSkills, a framework for representing, generating, and using reusable multimodal procedures for runtime visual decision making. Each MMSkill is a compact, state-conditioned package that couples a textual procedure with runtime state cards and multi-view keyframes. To construct these packages, we develop an agentic trajectory-to-skill Generator that transforms public non-evaluation trajectories into reusable multimodal skills through workflow grouping, procedure induction, visual grounding, and meta-skill-guided auditing. To use them, we introduce a branch-loaded multimodal skill agent: selected state cards and keyframes are inspected in a temporary branch, aligned with the live environment, and distilled into structured guidance for the main agent. Experiments across GUI and game-based visual-agent benchmarks show that MMSkills consistently improve both frontier and smaller multimodal agents, suggesting that external multimodal procedural knowledge complements model-internal priors.

Standard dual-encoder vision-language models that map images and text to deterministic points on a shared unit hypersphere through $\ell_2$ normalization typically expose neither \emph{aleatoric} uncertainty (cross-modal ambiguity) nor \emph{epistemic} uncertainty (lack of training-distribution support). Existing post-hoc methods either recover at most one of the two uncertainty components, or ignore the hyperspherical geometry of these models' embeddings. We propose \textbf{GeoFlowVLM} as a post-hoc adapter that learns the joint distribution of paired $\ell_2$-normalised dual-encoder VLM embeddings on the product hypersphere $\mathbb{S}^{d-1} \times \mathbb{S}^{d-1}$ via Riemannian flow matching with a single masked velocity field. A consistency result shows that, in the population limit, the trained network exposes the joint flow and both cross-modal conditional flows as valid Riemannian flow-matching velocity fields on their respective domains. We derive two quantities from this single model: a conditional retrieval entropy that quantifies aleatoric ambiguity with a decision-theoretic interpretation via a Fano-type bound, and a marginal-typicality epistemic score justified by an exact chain-rule decomposition of the joint NLL. This decomposition isolates a cross-modal pointwise-mutual-information term that is structurally discriminative rather than epistemic, and is empirically the only consistently uninformative standalone component. Empirically, the entropy tracks Recall@1 with near-ideal monotonic calibration across three retrieval benchmarks in both directions, and the marginal-typicality sum yields consistently calibrated selective accuracy across four zero-shot classification benchmarks.

Financial decision-making in multilingual settings demands accurate numerical reasoning grounded in diverse modalities, yet existing benchmarks largely overlook this high-stakes, real-world challenge, especially for Indic languages. We introduce FinVQA, a benchmark for evaluating financial numerical and multimodal reasoning in multilingual Indic contexts. FinVQA spans English, Hindi, Bengali, Marathi, Gujarati, and Tamil, and comprises 18,900 samples across 14 financial domains. The dataset captures diverse reasoning paradigms under realistic constraints, and is structured across three difficulty levels (easy, moderate, hard) and four question formats: multiple choice, fill-in-the-blank, table matching, and true/false. To address these challenges, we propose FIND, a framework that combines supervised fine-tuning with constraint-aware decoding to promote faithful numerical reasoning, robust multimodal grounding, and structured decision-making. Together, FinVQA and FIND establish a rigorous evaluation and modeling paradigm for high-stakes multilingual multimodal financial reasoning.

Kamon (family crests) are an important part of Japanese culture and a natural test case for compositional visual recognition: each crest combines a small number of symbolic choices, but the space of possible descriptions is sparse. We introduce KamonBench, a grammar-based image-to-structure benchmark with 20,000 synthetic composite crests and auxiliary component examples. Each composite crest is paired with a formal kamon description language - "kamon yōgo" - description, a segmented Japanese analysis, an English translation, and a non-linguistic program code. Because each synthetic crest is generated from known factors, namely container, modifier, and motif, KamonBench supports evaluation beyond caption-level accuracy: direct program-code factor metrics, controlled factor-pair recombination splits, counterfactual motif-sensitivity groups under fixed container-modifier contexts, and linear probes of factor accessibility. We include baseline results for a ViT encoder/Transformer decoder and two VGG n-gram decoders, with and without learned positional masks. KamonBench therefore provides a controlled testbed for sparse compositional visual recognition and factor recovery in vision-language models.

We present Supervised Deep Multimodal Matrix Factorization (SD3MF), an interpretable framework for integrative brain network analysis that generalizes Symmetric Nonnegative Matrix Tri-Factorization (SNMTF) from unsupervised single-graph clustering to supervised prediction over populations of multimodal graphs. SD3MF learns deep hierarchical factorizations for each modality together with a shared latent representation that aligns subjects across views. An encoder-decoder formulation jointly optimizes graph reconstruction and supervised prediction, while adaptive weights enable data-driven multimodal fusion. By representing each subject through community-level interaction matrices, the model yields interpretable and discriminative features. Experiments on multimodal connectome datasets show that SD3MF consistently outperforms strong deep learning baselines such as CNNs and GNNs, while enabling biologically interpretable insights. Code for reproducibility is available at: https://github.com/amjadseyedi/SD3MF.